ServersSupermicro SYS-420GU-TNXRServers

Universal 4U Dual Processor (Intel) GPU System with NVIDIA HGX™ A100 4-GPU SXM4 board, NVLINK™ GPU-GPU Interconnect, and Redundant 3000W Titanium Level Power Supplies.

SYS-420GU-TNXRAdvantages:

All-New Multi-Standard Architecture

Key Applications:

• High Performance Computing

• AI/Deep Learning Training

• Ultimate Modularity and Customization Options for AI and HPC Environments

• All-new modular architecture designed for flexibility and future proofing

• Optimal storage, networking, power, and cooling mix for top performance configurations

• Supports all major GPUs and CPUs, maximum CPU and GPU performance configurations, and all major GPU form factors and interfaces

• 10 Gen4 PCIe slots for fast networking devices

• 4U chassis supports up to 10x 2.5” NVMe/SATA drives

• Optional 1U expansion module for improved thermal capacity (up to 700W GPUs) and 2x AIOMs for networking

01Highly Flexible Platform

Supermicro’s Universal GPU System is the industry’s most advanced and flexible GPU server platform. Designed to deliver maximum compute power for large-scale AI deep learning and HPC workloads, this modular, open-standards based platform supports the industry’s most popular GPU technologies in a variety of form factors and combinations both today and into the future.

02Designed for Demanding HPC and AI Workloads

The Supermicro Universal GPU platform has been designed from the ground up to support a combination of CPU and GPU configurations, allowing customization for specific HPC and AI workloads within the data center using a single platform.
• High-performance computing including energy, molecular dynamics, physics, computational chemistry and climate sciences
• AI for image and video detection/recogintion, life sciences & drug discovery, autonomous driving and robitics

03Supports Industry-Standard GPU Form Factors

The Supermicro Universal GPU platform is designed to work with a wide range of GPUs based on an open standards design. By adhering to an agreed-upon set of hardware design standards, such as Universal Baseboard (UBB) and OCP Accelerator Modules (OAM), as well as PCI-E and platform-specific interfaces, IT administrators can choose the GPU architecture best suited for their HPC or AI workloads. Additionally, support for GPU interconnects including NVIDIA NVLink® and AMD Infinity Fabric™ facilitates ultra-fast GPU-toGPU communication, reducing bottlenecks caused by traditional GPU interlinks. The ability to handle both high-speed fabrics and standard PCI-E-based GPUs is a first for the industry

04Future Proof Design

The Universal GPU platform’s modular design and compatibility with a wide range of open-standard GPU interfaces allows for forward compatibility with next-generation GPU architectures without the need to replace or upgrade existing server infrastructure, thus reducing the cost of GPU upgrades. The platform has also been designed to easily acommodate nextgeneration CPU, memory and PCI-E technologies, reducing the cost and complexity of both development and deployment when such new technologies become available.

05Optional 1U Expansion Module

For the most demanding deployments, thermal performance and I/O of the standard 4U chassis can be further enhanced with an optional 1U add-on module. The resulting 5U configuration supports GPUs with TDP up to 700W and provides two additional OCP 3.0 AIOM slots for enhanced networking.